Abstract
Intracranial hemorrhage (ICH) is a life-threatening emergency with high rates of mortality and morbidity. Rapid and accurate detection of ICH is crucial for patients to get a timely treatment. In order to achieve the automatic diagnosis of ICH, most deep learning models rely on huge amounts of slice labels for training. Unfortunately, the manual annotation of CT slices by radiologists is time-consuming and costly. To diagnose ICH, in this work, we propose to use an attention-based multiple instance learning (Att-MIL) approach implemented through the combination of an attention-based convolutional neural network (Att-CNN) and a variational Gaussian process for multiple instance learning (VGPMIL). Only labels at scan-level are necessary for training. Our method (a) trains the model using scan labels and assigns each slice with an attention weight, which can be used to provide slice-level predictions, and (b) uses the VGPMIL model based on low-dimensional features extracted by the Att-CNN to obtain improved predictions both at slice and scan levels. To analyze the performance of the proposed approach, our model has been trained on 1150 scans from an RSNA dataset and evaluated on 490 scans from an external CQ500 dataset. Our method outperforms other methods using the same scan-level training and is able to achieve comparable or even better results than other methods relying on slice-level annotations.
This work has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska Curie grant agreement No 860627 (CLARIFY Project) and also from the Spanish Ministry of Science and Innovation under project PID2019-105142RB-C22.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
RSNA intracranial hemorrhage detection. https://kaggle.com/c/rsna-intracranial-hemorrhage-detection
Arbabshirani, M.R., et al.: Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration. NPJ Digital Med. 1(1), 1–7 (2018)
Burduja, M., Ionescu, R.T., Verga, N.: Accurate and efficient intracranial hemorrhage detection and subtype classification in 3D CT scans with convolutional and long short-term memory neural networks. Sensors 20(19), 5611 (2020)
Campanella, G., Silva, V.W.K., Fuchs, T.J.: Terabyte-scale deep multiple instance learning for classification and localization in pathology (2018)
Chang, P., et al.: Hybrid 3D/2D convolutional neural network for hemorrhage evaluation on head CT. AJNR Am. J. Neuroradiol. 39(9), 1609–1616 (2018)
Chilamkurthy, S., et al.: Development and validation of deep learning algorithms for detection of critical findings in head CT scans (2018)
Haußmann, M., Hamprecht, F., Kandemir, M.: Variational Bayesian multiple instance learning with gaussian processes. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 810–819 (2017)
Ilse, M., Tomczak, J.M., Welling, M.: Attention-based deep multiple instance learning (2018)
Jnawali, K., Arbabshirani, M.R., Rao, N., Patel, A.A.: Deep 3D convolution neural network for CT brain hemorrhage classification. In: Mori, K., Petrick, N. (eds.) Medical Imaging 2018: Computer-Aided Diagnosis, p. 47. SPIE (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017)
Monteiro, M., et al.: Multiclass semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study. Lancet Digital Health 2(6), e314–e322 (2020)
Nguyen, N.T., Tran, D.Q., Nguyen, N.T., Nguyen, H.Q.: A CNN-LSTM architecture for detection of intracranial hemorrhage on CT scans (2020)
Otite, F.O., Khandelwal, P., Malik, A.M., Chaturvedi, S., Sacco, R.L., Romano, J.G.: Ten-year temporal trends in medical complications after acute intracerebral hemorrhage in the united states. Stroke 48(3), 596–603 (2017)
Patel, A., Leemput, S.C.v.d., Prokop, M., Ginneken, B.V., Manniesing, R.: Image level training and prediction: intracranial hemorrhage identification in 3D non-contrast CT. IEEE Access 7, 92355–92364 (2019)
Remedios, S., et al.: Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection. In: Medical Imaging 2020: Image Processing, vol. 11313, p. 113130F (2020)
Saab, K., et al.: Doubly weak supervision of deep learning models for head CT. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11766, pp. 811–819. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32248-9_90
Sato, D., et al.: A primitive study on unsupervised anomaly detection with an autoencoder in emergency head CT volumes. In: Medical Imaging 2018: Computer-Aided Diagnosis, p. 60 (2018)
Sobrino, J., Shafi, S.: Timing and causes of death after injuries, vol. 26, no. 2, pp. 120–123 (2013)
Titano, J.J., et al.: Automated deep-neural-network surveillance of cranial images for acute neurologic events. Nat. Med. 24(9), 1337–1341 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, Y., Schmidt, A., Hernández-Sánchez, E., Molina, R., Katsaggelos, A.K. (2021). Combining Attention-Based Multiple Instance Learning and Gaussian Processes for CT Hemorrhage Detection. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12902. Springer, Cham. https://doi.org/10.1007/978-3-030-87196-3_54
Download citation
DOI: https://doi.org/10.1007/978-3-030-87196-3_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87195-6
Online ISBN: 978-3-030-87196-3
eBook Packages: Computer ScienceComputer Science (R0)